INDEX

Explanations

words related to conversations and interactions among individuals

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Хьажоргаш

-0.59

Istorija

-0.58

DrawerLayout

-0.54

CodedInputStream

-0.51

ьаж

-0.48

IInterface

-0.47

#+#

-0.47

ceptre

-0.46

Джерело

-0.46

 nakalista

-0.45

POSITIVE LOGITS

setVerticalGroup

0.60

grill

0.57

 grill

0.56

matchCondition

0.56

 للمعارف

0.55

LookAnd

0.53

SourceChecksum

0.53

WebVitals

0.52

aco

0.52

HasAnnotation

0.51

Activations Density 0.379%

words related to conversations and interactions among individuals

No Comments

No Known Activations